{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QXYOR7RYE4MMP66YQVBNPBXRP6","short_pith_number":"pith:QXYOR7RY","schema_version":"1.0","canonical_sha256":"85f0e8fe382718c7fbd88542d786f17f8cdf819486584f62eced73a8ab3b9a85","source":{"kind":"arxiv","id":"1703.03664","version":1},"attestation_state":"computed","paper":{"title":"Parallel Multiscale Autoregressive Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"A\\\"aron van den Oord, Dan Belov, Nal Kalchbrenner, Nando de Freitas, Scott Reed, Sergio G\\'omez Colmenarejo, Ziyu Wang","submitted_at":"2017-03-10T12:58:23Z","abstract_excerpt":"PixelCNN achieves state-of-the-art results in density estimation for natural images. Although training is fast, inference is costly, requiring one network evaluation per pixel; O(N) for N pixels. This can be sped up by caching activations, but still involves generating each pixel sequentially. In this work, we propose a parallelized PixelCNN that allows more efficient inference by modeling certain pixel groups as conditionally independent. Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1703.03664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-10T12:58:23Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"8583877b164b0bcb16ec090ac89e02fe1839e3fe62a45c57865c33637d19259f","abstract_canon_sha256":"4bbcfb57b66fa9eee9c0f7e0aeddebd43d1afad72b64333dabc500b6a791f8fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:58.399964Z","signature_b64":"W9g8rP6c2zXftwRTaSwjhj7wsJpM6nNRo4aoxCDmW3tCIr+aEKa1ga4hLnjhSQf+vyWOqdL1JZ0kK6P7Y1TJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85f0e8fe382718c7fbd88542d786f17f8cdf819486584f62eced73a8ab3b9a85","last_reissued_at":"2026-05-18T00:48:58.399296Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:58.399296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel Multiscale Autoregressive Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"A\\\"aron van den Oord, Dan Belov, Nal Kalchbrenner, Nando de Freitas, Scott Reed, Sergio G\\'omez Colmenarejo, Ziyu Wang","submitted_at":"2017-03-10T12:58:23Z","abstract_excerpt":"PixelCNN achieves state-of-the-art results in density estimation for natural images. Although training is fast, inference is costly, requiring one network evaluation per pixel; O(N) for N pixels. This can be sped up by caching activations, but still involves generating each pixel sequentially. In this work, we propose a parallelized PixelCNN that allows more efficient inference by modeling certain pixel groups as conditionally independent. Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03664","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.03664","created_at":"2026-05-18T00:48:58.399404+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.03664v1","created_at":"2026-05-18T00:48:58.399404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03664","created_at":"2026-05-18T00:48:58.399404+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXYOR7RYE4MM","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXYOR7RYE4MMP66Y","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXYOR7RY","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1904.10509","citing_title":"Generating Long Sequences with Sparse Transformers","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6","json":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6.json","graph_json":"https://pith.science/api/pith-number/QXYOR7RYE4MMP66YQVBNPBXRP6/graph.json","events_json":"https://pith.science/api/pith-number/QXYOR7RYE4MMP66YQVBNPBXRP6/events.json","paper":"https://pith.science/paper/QXYOR7RY"},"agent_actions":{"view_html":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6","download_json":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6.json","view_paper":"https://pith.science/paper/QXYOR7RY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.03664&json=true","fetch_graph":"https://pith.science/api/pith-number/QXYOR7RYE4MMP66YQVBNPBXRP6/graph.json","fetch_events":"https://pith.science/api/pith-number/QXYOR7RYE4MMP66YQVBNPBXRP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6/action/storage_attestation","attest_author":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6/action/author_attestation","sign_citation":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6/action/citation_signature","submit_replication":"https://pith.science/pith/QXYOR7RYE4MMP66YQVBNPBXRP6/action/replication_record"}},"created_at":"2026-05-18T00:48:58.399404+00:00","updated_at":"2026-05-18T00:48:58.399404+00:00"}